przemyslaw.jacewicz
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

code formatting

This commit is contained in:
Claudio Atzori 2023-02-22 10:15:25 +01:00
parent 3b876d9327
commit 0c1be41b30
2 changed files with 253 additions and 251 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/usagestats/SparkAtomicActionUsageJob.java
View File

@ -8,13 +8,12 @@ import java.io.Serializable;
import java.util.Arrays;
import java.util.List;
import java.util.Optional;
import eu.dnetlib.dhp.schema.oaf.*;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SaveMode;
@ -28,6 +27,7 @@ import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
import scala.Tuple2;
@ -80,12 +80,12 @@ public class SparkAtomicActionUsageJob implements Serializable {
});
}
private static void prepareData(String dbname, SparkSession spark, String workingPath, String tableName, String attribute_name) {
private static void prepareData(String dbname, SparkSession spark, String workingPath, String tableName,
String attribute_name) {
spark
.sql(
"Select " + attribute_name + " as id, sum(downloads) as downloads, sum(views) as views " +
"from " + dbname + "." + tableName +
"group by " + attribute_name)
.sql(String.format(
"select %s as id, sum(downloads) as downloads, sum(views) as views " +
"from %s.%s group by %s", attribute_name, dbname, tableName, attribute_name))
.as(Encoders.bean(UsageStatsModel.class))
.write()
.mode(SaveMode.Overwrite)
@ -93,16 +93,16 @@ public class SparkAtomicActionUsageJob implements Serializable {
.json(workingPath);
}
public static void writeActionSet(SparkSession spark, String inputPath, String outputPath) {
getFinalIndicatorsResult(spark, inputPath+ "/usageDb").
toJavaRDD().
map(p -> new AtomicAction(p.getClass(),p))
.union(getFinalIndicatorsProject(spark, inputPath + "/projectDb")
getFinalIndicatorsResult(spark, inputPath + "/usageDb")
.toJavaRDD()
.map(p -> new AtomicAction(p.getClass(), p))
.union(
getFinalIndicatorsProject(spark, inputPath + "/projectDb")
.toJavaRDD()
.map(p -> new AtomicAction(p.getClass(), p)))
.union(getFinalIndicatorsDatasource(spark, inputPath + "/datasourceDb")
.union(
getFinalIndicatorsDatasource(spark, inputPath + "/datasourceDb")
.toJavaRDD()
.map(p -> new AtomicAction(p.getClass(), p)))
.mapToPair(
@ -127,10 +127,10 @@ public class SparkAtomicActionUsageJob implements Serializable {
return readPath(spark, inputPath, UsageStatsModel.class)
.map((MapFunction<UsageStatsModel, Project>) usm -> {
Project r = new Project();
r.setId("40|" + usm.getId());
r.setMeasures(getMeasure(usm.getDownloads(), usm.getViews()));
return r;
Project p = new Project();
p.setId("40|" + usm.getId());
p.setMeasures(getMeasure(usm.getDownloads(), usm.getViews()));
return p;
}, Encoders.bean(Project.class));
}
@ -138,15 +138,13 @@ public class SparkAtomicActionUsageJob implements Serializable {
return readPath(spark, inputPath, UsageStatsModel.class)
.map((MapFunction<UsageStatsModel, Datasource>) usm -> {
Datasource r = new Datasource();
r.setId("10|" + usm.getId());
r.setMeasures(getMeasure(usm.getDownloads(), usm.getViews()));
return r;
Datasource d = new Datasource();
d.setId("10|" + usm.getId());
d.setMeasures(getMeasure(usm.getDownloads(), usm.getViews()));
return d;
}, Encoders.bean(Datasource.class));
}
private static List<Measure> getMeasure(Long downloads, Long views) {
DataInfo dataInfo = OafMapperUtils
.dataInfo(

12
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/usagestats/SparkAtomicActionCountJobTest.java
View File

@ -8,7 +8,6 @@ import java.nio.file.Files;
import java.nio.file.Path;
import java.util.stream.Collectors;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import org.apache.commons.io.FileUtils;
import org.apache.hadoop.io.Text;
import org.apache.spark.SparkConf;
@ -25,6 +24,7 @@ import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.schema.oaf.Result;
public class SparkAtomicActionCountJobTest {
@ -160,7 +160,13 @@ public class SparkAtomicActionCountJobTest {
Assertions
.assertEquals(
1, tmp.filter(r -> ((OafEntity)r.getPayload()).getId().equals("50|dedup_wf_001::53575dc69e9ace947e02d47ecd54a7a6")).count());
1,
tmp
.filter(
r -> ((OafEntity) r.getPayload())
.getId()
.equals("50|dedup_wf_001::53575dc69e9ace947e02d47ecd54a7a6"))
.count());
Assertions
.assertEquals(
@ -261,7 +267,6 @@ public class SparkAtomicActionCountJobTest {
.get(0)
.getValue());
Assertions
.assertEquals(
"0",
@ -361,7 +366,6 @@ public class SparkAtomicActionCountJobTest {
.get(0)
.getValue());
Assertions
.assertEquals(
"0",